Inspiration
when i started doing reports since i came to college, and once i had to do a report for a project and our project incharge was not available all the time to correct and giving feedback so we thought why cant we make ai based anaylises and gives feed baclk
What it does
it uses ai to analyze and gives feedback and changes needed in the report
How we built it
We developed ReportX using a modular approach. The frontend was created with HTML, CSS, and JavaScript, while the backend was implemented using Node.js to handle report analysis. We integrated the Gemini AI API to provide automated feedback on uploaded reports. Each module was tested individually before combining them into the final system.
Challenges we ran into
One of the main challenges was parsing PDF and DOCX files consistently across different browsers. Another challenge was ensuring the AI-generated recommendations were relevant and accurate. Handling API limits for the Gemini model also required careful management to avoid request failures.
Accomplishments that we're proud of
We successfully built a fully functional prototype that can analyze reports and provide structured feedback, including issues, recommendations, and guidance. The interface is user-friendly, allowing users to upload documents, select report formats, and view AI analysis results seamlessly.
What we learned
We gained experience integrating AI services with a web application, handling asynchronous requests, and parsing document formats. We also learned the importance of designing clear prompts for AI models to produce structured and reliable outputs.
What's next for ReportX
Future improvements include adding support for more file formats, improving AI feedback accuracy, and implementing real-time collaboration features. We also plan to deploy the system fully on a cloud platform and enhance the dashboard with more detailed analytics for users.
Log in or sign up for Devpost to join the conversation.